| Age | Commit message (Expand) | Author |
|---|
| 4 days | Blog (Claude's review): add 'short version' TL;DR up top for wider audience; ... | Void Agent |
| 4 days | Blog: fill in public repo URL (git.jayrup.me/c/jspace-nanogpt.git) | Void Agent |
| 4 days | Robustness confirmed: freq correlation identical under Anthropic's exact esti... | Void Agent |
| 4 days | Fix in-word metric: strict (both-sides, 58% random / 0% clean) vs touches (95... | Void Agent |
| 4 days | synthetic_pair: add --clean boundary mode (noise token at word starts) + conf... | Void Agent |
| 4 days | Loss-reweighting results: q/control 0.944 (CI crosses 1), q/ctrl_random 0.985... | Void Agent |
| 4 days | Add willkn GreaterWrong corroboration: independent GPT-2-medium finding that ... | Void Agent |
| 4 days | Verify against Anthropic's official jacobian-lens repo: estimator match, zero... | Void Agent |
| 4 days | test_jlens_v3: move tiny model to DEV (fix cpu/cuda mismatch on cuda runs) | Void Agent |
| 4 days | Address Luna repo review: dynamic repo root (no hardcoded cwd), J-lens correc... | Void Agent |
| 4 days | Add src/stats_decomp.py: reproducible W_U decomposition, p-values, Spearman, ... | Void Agent |
| 4 days | Document n_pairs denominator (exact count) and ctrl_random gradient-mass cave... | Void Agent |
| 4 days | Address Gemini+Opus repo reviews: W_U decomposition, Spearman+p-values, synth... | Void Agent |
| 4 days | Blog: fact-check section — 3 independent checks confirm Anthropic has no fr... | Void Agent |
| 4 days | Docs: Feynman-style blog draft, MIT license, requirements, results.md, README... | Void Agent |
| 4 days | Add canonical test command: scripts/test.sh (runs tests/test_loss_reweight.py... | Void Agent |
| 4 days | loss_reweight: pass Y to forward for full logits (Karpathy nanoGPT returns la... | Void Agent |
| 4 days | Add tests/test_loss_reweight.py: batch determinism + weighting semantics (run... | Void Agent |
| 4 days | loss_reweight: CPU generators for randint/randperm (CUDA generators unsupport... | Void Agent |
| 4 days | Add causal experiments: synthetic frequency-matched pair (Gemini design) + lo... | Void Agent |
| 6 days | jlens_v3: chunk VJP probes (16) to fit K2200 4GB; proxy chunk fix; e2e verifi... | Void Agent |
| 6 days | Add faithful J-lens (jlens_v3): W_U-probed residual Jacobian per paper; both-... | Void Agent |
| 7 days | GPT-2 J-lens: use local Shakespeare + fix summary | Void Agent |
| 7 days | GPT-2 Small J-lens: frequency + dimensionality sampling | Void Agent |
| 7 days | Add Pythia-70m test script | Void Agent |
| 7 days | Fix: lr→learning_rate in configure_optimizers | Void Agent |
| 7 days | Add dimensional starvation experiment (d_model=16,32,64,128 vs 384) | Void Agent |
| 7 days | Add controlled frequency ablation experiment (doubled-q) | Void Agent |
| 8 days | jlens_v2: fix import path for src/ -> root layout | Void Agent |
| 8 days | Add jlens_v2.py: simplified gradient approach for J-lens | Void Agent |
| 8 days | jlens.py: fix hooks — don't detach activations, preserve gradient graph | Void Agent |
| 8 days | jlens.py: fix load_model for dict-format nanoGPT checkpoints | Void Agent |
| 8 days | Fix jlens.py import path: src/ -> project root | Void Agent |
| 8 days | Maxwell GPU fixes: disable bf16 SDPA, force fp32 | Void Agent |
| 8 days | Restructure: nanoGPT at root, custom code in src/ | Void Agent |
| 8 days | Initial project setup: J-lens implementation for nanoGPT | Void Agent |
